Learning Predictive Visuomotor Coordination

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Jia, Wenqi, Lai, Bolin, Liu, Miao, Xu, Danfei, Rehg, James M.
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866908290078736384
author Jia, Wenqi
Lai, Bolin
Liu, Miao
Xu, Danfei
Rehg, James M.
author_facet Jia, Wenqi
Lai, Bolin
Liu, Miao
Xu, Danfei
Rehg, James M.
contents Understanding and predicting human visuomotor coordination is crucial for applications in robotics, human-computer interaction, and assistive technologies. This work introduces a forecasting-based task for visuomotor modeling, where the goal is to predict head pose, gaze, and upper-body motion from egocentric visual and kinematic observations. We propose a \textit{Visuomotor Coordination Representation} (VCR) that learns structured temporal dependencies across these multimodal signals. We extend a diffusion-based motion modeling framework that integrates egocentric vision and kinematic sequences, enabling temporally coherent and accurate visuomotor predictions. Our approach is evaluated on the large-scale EgoExo4D dataset, demonstrating strong generalization across diverse real-world activities. Our results highlight the importance of multimodal integration in understanding visuomotor coordination, contributing to research in visuomotor learning and human behavior modeling.
format Preprint
id arxiv_https___arxiv_org_abs_2503_23300
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Learning Predictive Visuomotor Coordination
Jia, Wenqi
Lai, Bolin
Liu, Miao
Xu, Danfei
Rehg, James M.
Computer Vision and Pattern Recognition
Robotics
Understanding and predicting human visuomotor coordination is crucial for applications in robotics, human-computer interaction, and assistive technologies. This work introduces a forecasting-based task for visuomotor modeling, where the goal is to predict head pose, gaze, and upper-body motion from egocentric visual and kinematic observations. We propose a \textit{Visuomotor Coordination Representation} (VCR) that learns structured temporal dependencies across these multimodal signals. We extend a diffusion-based motion modeling framework that integrates egocentric vision and kinematic sequences, enabling temporally coherent and accurate visuomotor predictions. Our approach is evaluated on the large-scale EgoExo4D dataset, demonstrating strong generalization across diverse real-world activities. Our results highlight the importance of multimodal integration in understanding visuomotor coordination, contributing to research in visuomotor learning and human behavior modeling.
title Learning Predictive Visuomotor Coordination
topic Computer Vision and Pattern Recognition
Robotics
url https://arxiv.org/abs/2503.23300